Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and discourse markers in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    line
    -0.17
    rie
    -0.15
     Dj
    -0.15
    ije
    -0.14
    itat
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    addtogroup
    -0.14
    riel
    -0.13
    ric
    -0.13
     Selection
    -0.13
    POSITIVE LOGITS
    oxy
    0.16
    зÑĮ
    0.15
    елей
    0.15
    chw
    0.14
    ossier
    0.14
    aper
    0.14
     euler
    0.14
    apes
    0.14
    uales
    0.14
    /problems
    0.14
    Act Density 0.000%

    No Known Activations